Fully automated deep learning-based localization and segmentation of the locus coeruleus in aging and Parkinson's disease using neuromelanin-sensitive MRI

Neuromelanin-sensitive MRI for mechanistic research and biomarker development in psychiatry

Neuromelanin-sensitive MRI is a burgeoning non-invasive neuroimaging method with an increasing number of applications in psychiatric research. This MRI modality is sensitive to the concentration of neuromelanin, which is synthesized from intracellular catecholamines and accumulates in catecholaminergic nuclei including the dopaminergic substantia nigra and the noradrenergic locus coeruleus. Emerging data suggest the utility of neuromelanin-sensitive MRI as a proxy measure for variability in catecholamine metabolism and function, even in the absence of catecholaminergic cell loss. Given the importance of catecholamine function to several psychiatric disorders and their treatments, neuromelanin-sensitive MRI is ideally positioned as an informative and easy-to-acquire catecholaminergic index. In this review paper, we examine basic aspects of neuromelanin and neuromelanin-sensitive MRI and focus on its psychiatric applications in the contexts of mechanistic research and biomarker development. We discuss ongoing debates and state-of-the-art research into the mechanisms of the neuromelanin-sensitive MRI contrast, standardized protocols and optimized analytic approaches, and application of cutting-edge methods such as machine learning and artificial intelligence to enhance the feasibility and predictive power of neuromelanin-sensitive-MRI-based tools. We finally lay out important future directions to allow neuromelanin-sensitive-MRI to fulfill its potential as a key component of the research, and ultimately clinical, toolbox in psychiatry.

Automatic Segmentation and Quantification of Nigrosome-1 Neuromelanin and Iron in MRI: A Candidate Biomarker for Parkinson's Disease

BACKGROUND

There is a lack of automated tools for the segmentation and quantification of neuromelanin (NM) and iron in the nigrosome-1 (N1). Existing tools evaluate the N1 sign, i.e., the presence or absence of the "swallow-tail" in iron-sensitive MRI, or globally analyze the MRI signal in an area containing the N1, without providing a volumetric delineation.

PURPOSE

Present an automated method to segment the N1 and quantify differences in N1's NM and iron content between Parkinson's disease (PD) patients and healthy controls (HCs). Study whether N1 degeneration is clinically related to PD and could be used as a biomarker of the disease.

STUDY TYPE

Prospective.

SUBJECTS

Seventy-one PD (65.3 ± 10.3 years old, 34 female/37 male); 30 HC (62.7 ± 7.8 years old, 17 female/13 male).

FIELD STRENGTH/SEQUENCE

3 T Anatomical T1-weighted MPRAGE, NM-MRI T1-weighted gradient with magnetization transfer, susceptibility-weighted imaging (SWI).

ASSESSMENT

N1 was automatically segmented in SWI images using a multi-image atlas, populated with healthy N1 structures manually annotated by a neurologist. Relative NM and iron content were quantified and their diagnostic performance assessed and compared with the substantia nigra pars compacta (SNc). The association between image parameters and clinically relevant variables was studied.

STATISTICAL TESTS

Nonparametric tests were used (Mann-Whitney's U, chi-square, and Friedman tests) at P = 0.05.

RESULTS

N1's relative NM content decreased and relative iron content increased in PD patients compared with HCs (NM-CRHC = 22.55 ± 1.49; NM-CRPD = 19.79 ± 1.92; NM-nVolHC = 2.69 × 10-5 ± 1.02 × 10-5; NM-nVolPD = 1.18 × 10-5 ± 0.96 × 10-5; Iron-CRHC = 10.51 ± 2.64; Iron-CRPD = 19.35 ± 7.88; Iron-nVolHC = 0.72 × 10-5 ± 0.81 × 10-5; Iron-nVolPD = 2.82 × 10-5 ± 2.04 × 10-5). Binary logistic regression analyses combining N1 and SNc image parameters yielded a top AUC = 0.955. Significant correlation was found between most N1 parameters and both disease duration (ρNM-CR = -0.31; ρiron-CR = 0.43; ρiron-nVol = 0.46) and the motor status (ρNM-nVol = -0.27; ρiron-CR = 0.33; ρiron-nVol = 0.28), suggesting NM reduction along with iron accumulation in N1 as the disease progresses.

DATA CONCLUSION

This method provides a fully automatic N1 segmentation, and the analyses performed reveal that N1 relative NM and iron quantification improves diagnostic performance and suggest a relative NM reduction along with a relative iron accumulation in N1 as the disease progresses.

EVIDENCE LEVEL

1 TECHNICAL EFFICACY: Stage 1.

Fully Automated MRI-based Analysis of the Locus Coeruleus in Aging and Alzheimer's Disease Dementia using ELSI-Net

INTRODUCTION

The Locus Coeruleus (LC) is linked to the development and pathophysiology of neurodegenerative diseases such as Alzheimer's Disease (AD). Magnetic Resonance Imaging based LC features have shown potential to assess LC integrity in vivo.

METHODS

We present a Deep Learning based LC segmentation and feature extraction method: ELSI-Net and apply it to healthy aging and AD dementia datasets. Agreement to expert raters and previously published LC atlases were assessed. We aimed to reproduce previously reported differences in LC integrity in aging and AD dementia and correlate extracted features to cerebrospinal fluid (CSF) biomarkers of AD pathology.

RESULTS

ELSI-Net demonstrated high agreement to expert raters and published atlases. Previously reported group differences in LC integrity were detected and correlations to CSF biomarkers were found.

DISCUSSION

Although we found excellent performance, further evaluations on more diverse datasets from clinical cohorts are required for a conclusive assessment of ELSI-Nets general applicability.

Automatic geometry-based estimation of the locus coeruleus region on T1-weighted magnetic resonance images

The locus coeruleus (LC) is a key brain structure implicated in cognitive function and neurodegenerative disease. Automatic segmentation of the LC is a crucial step in quantitative non-invasive analysis of the LC in large MRI cohorts. Most publicly available imaging databases for training automatic LC segmentation models take advantage of specialized contrast-enhancing (e.g., neuromelanin-sensitive) MRI. Segmentation models developed with such image contrasts, however, are not readily applicable to existing datasets with conventional MRI sequences. In this work, we evaluate the feasibility of using non-contrast neuroanatomical information to geometrically approximate the LC region from standard 3-Tesla T1-weighted images of 20 subjects from the Human Connectome Project (HCP). We employ this dataset to train and internally/externally evaluate two automatic localization methods, the Expected Label Value and the U-Net. For out-of-sample segmentation, we compare the results with atlas-based segmentation, as well as test the hypothesis that using the phase image as input can improve the robustness. We then apply our trained models to a larger subset of HCP, while exploratorily correlating LC imaging variables and structural connectivity with demographic and clinical data. This report provides an evaluation of computational methods estimating neural structure.

Deep Learning-based Approach for Brainstem and Ventricular MR Planimetry: Application in Patients with Progressive Supranuclear Palsy

Purpose To develop a fast and fully automated deep learning (DL)-based method for the MRI planimetric segmentation and measurement of the brainstem and ventricular structures most affected in patients with progressive supranuclear palsy (PSP). Materials and Methods In this retrospective study, T1-weighted MR images in healthy controls (n = 84) were used to train DL models for segmenting the midbrain, pons, middle cerebellar peduncle (MCP), superior cerebellar peduncle (SCP), third ventricle, and frontal horns (FHs). Internal, external, and clinical test datasets (n = 305) were used to assess segmentation model reliability. DL masks from test datasets were used to automatically extract midbrain and pons areas and the width of MCP, SCP, third ventricle, and FHs. Automated measurements were compared with those manually performed by an expert radiologist. Finally, these measures were combined to calculate the midbrain to pons area ratio, MR parkinsonism index (MRPI), and MRPI 2.0, which were used to differentiate patients with PSP (n = 71) from those with Parkinson disease (PD) (n = 129). Results Dice coefficients above 0.85 were found for all brain regions when comparing manual and DL-based segmentations. A strong correlation was observed between automated and manual measurements (Spearman ρ > 0.80, P < .001). DL-based measurements showed excellent performance in differentiating patients with PSP from those with PD, with an area under the receiver operating characteristic curve above 0.92. Conclusion The automated approach successfully segmented and measured the brainstem and ventricular structures. DL-based models may represent a useful approach to support the diagnosis of PSP and potentially other conditions associated with brainstem and ventricular alterations. Keywords: MR Imaging, Brain/Brain Stem, Segmentation, Quantification, Diagnosis, Convolutional Neural Network Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Mohajer in this issue.

Neuromelanin-sensitive MRI as a promising biomarker of catecholamine function

Disruptions to dopamine and noradrenergic neurotransmission are noted in several neurodegenerative and psychiatric disorders. Neuromelanin-sensitive (NM)-MRI offers a non-invasive approach to visualize and quantify the structural and functional integrity of the substantia nigra and locus coeruleus. This method may aid in the diagnosis and quantification of longitudinal changes of disease and could provide a stratification tool for predicting treatment success of pharmacological interventions targeting the dopaminergic and noradrenergic systems. Given the growing clinical interest in NM-MRI, understanding the contrast mechanisms that generate this signal is crucial for appropriate interpretation of NM-MRI outcomes and for the continued development of quantitative MRI biomarkers that assess disease severity and progression. To date, most studies associate NM-MRI measurements to the content of the neuromelanin pigment and/or density of neuromelanin-containing neurons, while recent studies suggest that the main source of the NM-MRI contrast is not the presence of neuromelanin but the high-water content in the dopaminergic and noradrenergic neurons. In this review, we consider the biological and physical basis for the NM-MRI contrast and discuss a wide range of interpretations of NM-MRI. We describe different acquisition and image processing approaches and discuss how these methods could be improved and standardized to facilitate large-scale multisite studies and translation into clinical use. We review the potential clinical applications in neurological and psychiatric disorders and the promise of NM-MRI as a biomarker of disease, and finally, we discuss the current limitations of NM-MRI that need to be addressed before this technique can be utilized as a biomarker and translated into clinical practice and offer suggestions for future research.

Automatic Geometry-based Estimation of the Locus Coeruleus Region on T1-Weighted Magnetic Resonance Images

The locus coeruleus (LC) is a key brain structure implicated in cognitive function and neurodegenerative disease. Automatic segmentation of the LC is a crucial step in quantitative non-invasive analysis of the LC in large MRI cohorts. Most publicly available imaging databases for training automatic LC segmentation models take advantage of specialized contrast-enhancing (e.g., neuromelanin-sensitive) MRI. Segmentation models developed with such image contrasts, however, are not readily applicable to existing datasets with conventional MRI sequences. In this work, we evaluate the feasibility of using non-contrast neuroanatomical information to geometrically approximate the LC region from standard 3-Tesla T1-weighted images of 20 subjects from the Human Connectome Project (HCP). We employ this dataset to train and internally/externally evaluate two automatic localization methods, the Expected Label Value and the U-Net. We also test the hypothesis that using the phase image as input can improve the robustness of out-of-sample segmentation. We then apply our trained models to a larger subset of HCP, while exploratorily correlating LC imaging variables and structural connectivity with demographic and clinical data. This report contributes and provides an evaluation of two computational methods estimating neural structure.

Rostral-middle locus coeruleus integrity and subjective cognitive decline in early old age

OBJECTIVES

Abnormal tau, a hallmark Alzheimer's disease (AD) pathology, may appear in the locus coeruleus (LC) decades before AD symptom onset. Reports of subjective cognitive decline are also often present prior to formal diagnosis. Yet, the relationship between LC structural integrity and subjective cognitive decline has remained unexplored. Here, we aimed to explore these potential associations.

METHODS

We examined 381 community-dwelling men (mean age = 67.58; SD = 2.62) in the Vietnam Era Twin Study of Aging who underwent LC-sensitive magnetic resonance imaging and completed the Everyday Cognition scale to measure subjective cognitive decline along with their selected informants. Mixed models examined the associations between rostral-middle and caudal LC integrity and subjective cognitive decline after adjusting for depressive symptoms, physical morbidities, and family. Models also adjusted for current objective cognitive performance and objective cognitive decline to explore attenuation.

RESULTS

For participant ratings, lower rostral-middle LC contrast to noise ratio (LCCNR) was associated with significantly greater subjective decline in memory, executive function, and visuospatial abilities. For informant ratings, lower rostral-middle LCCNR was associated with significantly greater subjective decline in memory only. Associations remained after adjusting for current objective cognition and objective cognitive decline in respective domains.

CONCLUSIONS

Lower rostral-middle LC integrity is associated with greater subjective cognitive decline. Although not explained by objective cognitive performance, such a relationship may explain increased AD risk in people with subjective cognitive decline as the LC is an important neural substrate important for higher order cognitive processing, attention, and arousal and one of the first sites of AD pathology.

NigraNet: An automatic framework to assess nigral neuromelanin content in early Parkinson's disease using convolutional neural network

BACKGROUND

Parkinson's disease (PD) demonstrates neurodegenerative changes in the substantia nigra pars compacta (SNc) using neuromelanin-sensitive (NM)-MRI. As SNc manual segmentation is prone to substantial inter-individual variability across raters, development of a robust automatic segmentation framework is necessary to facilitate nigral neuromelanin quantification. Artificial intelligence (AI) is gaining traction in the neuroimaging community for automated brain region segmentation tasks using MRI.

OBJECTIVE

Developing and validating AI-based NigraNet, a fully automatic SNc segmentation framework allowing nigral neuromelanin quantification in patients with PD using NM-MRI.

METHODS

We prospectively included 199 participants comprising 144 early-stage idiopathic PD patients (disease duration = 1.5 ± 1.0 years) and 55 healthy volunteers (HV) scanned using a 3 Tesla MRI including whole brain T1-weighted anatomical imaging and NM-MRI. The regions of interest (ROI) were delineated in all participants automatically using NigraNet, a modified U-net, and compared to manual segmentations performed by two experienced raters. The SNc volumes (Vol), volumes corrected by total intracranial volume (Cvol), normalized signal intensity (NSI) and contrast-to-noise ratio (CNR) were computed. One-way GLM-ANCOVA was performed while adjusting for age and sex as covariates. Diagnostic performance measurement was assessed using the receiver operating characteristic (ROC) analysis. Inter and intra-observer variability were estimated using Dice similarity coefficient (DSC). The agreements between methods were tested using intraclass correlation coefficient (ICC) based on a mean-rating, two-way, mixed-effects model estimates for absolute agreement. Cronbach's alpha and Bland-Altman plots were estimated to assess inter-method consistency.

RESULTS

Using both methods, Vol, Cvol, NSI and CNR measurements differed between PD and HV with an effect of sex for Cvol and CNR. ICC values between the methods demonstrated optimal agreement for Cvol and CNR (ICC > 0.9) and high reproducibility (DSC: 0.80) was also obtained. The SNc measurements also showed good to excellent consistency values (Cronbach's alpha > 0.87). Bland-Altman plots of agreement demonstrated no association of SNc ROI measurement differences between the methods and ROI average measurements while confirming that 95 % of the data points were ranging between the limits of mean difference (d ± 1.96xSD). Percentage changes between PD and HV were -27.4 % and -17.7 % for Vol, -30.0 % and -22.2 % for Cvol, -15.8 % and -14.4 % for NSI, -17.1 % and -16.0 % for CNR for automatic and manual measurements respectively. Using automatic method, in the entire dataset, we obtained the areas under the ROC curve (AUC) of 0.83 for Vol, 0.85 for Cvol, 0.79 for NSI and 0.77 for CNR whereas in the training dataset of 0.96 for Vol, 0.95 for Cvol, 0.85 for NSI and 0.85 for CNR. Disease duration correlated negatively with NSI of the patients for both the automatic and manual measurements.

CONCLUSIONS

We presented an AI-based NigraNet framework that utilizes a small MRI training dataset to fully automatize the SNc segmentation procedure with an increased precision and more reproducible results. Considering the consistency, accuracy and speed of our approach, this study could be a crucial step towards the implementation of a time-saving non-rater dependent fully automatic method for studying neuromelanin changes in clinical settings and large-scale neuroimaging studies.